Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5026 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.9367. Min Act: -0.1700
Data Index: 8095713 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.8742. Min Act: -0.1700
Data Index: 3456085 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.8742. Min Act: -0.1700
Data Index: 3845479 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.8117. Min Act: -0.1700
Data Index: 6828174 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.7804. Min Act: -0.1700
Data Index: 4245458 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.7179. Min Act: -0.1700
Data Index: 3845480 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.6554. Min Act: -0.1700
Data Index: 2259464 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.6554. Min Act: -0.1700
Data Index: 6566760 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.6554. Min Act: -0.1700
Data Index: 5401916 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.6554. Min Act: -0.1700
Data Index: 7416292 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.6242. Min Act: -0.1700
Data Index: 5111454 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.5929. Min Act: -0.1700
Data Index: 4762484 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.5929. Min Act: -0.1700
Data Index: 3098380 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.5929. Min Act: -0.1700
Data Index: 7599179 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.5617. Min Act: -0.1700
Data Index: 3621038 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.5617. Min Act: -0.1700
Data Index: 5660002 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.4992. Min Act: -0.1700
Data Index: 7016801 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.5304. Min Act: -0.1700
Data Index: 4470535 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.5304. Min Act: -0.1700
Data Index: 2499554 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9367. Min Range: -5.9367
Max Act: 5.5304. Min Act: -0.1700
Data Index: 1423276 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19